Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 7, 2026

Comprehensive DNA Methylation Analysis Using a Methyl-CpG-binding Domain Capture-based Method in Chronic Lymphocytic Leukemia Patients
13:21

Comprehensive DNA Methylation Analysis Using a Methyl-CpG-binding Domain Capture-based Method in Chronic Lymphocytic Leukemia Patients

Published on: June 16, 2017

Generalized query-based active learning to identify differentially methylated regions in DNA.

Md Muksitul Haque1, Lawrence B Holder, Michael K Skinner

  • 1Washington State University, Pullman.

IEEE/ACM Transactions on Computational Biology and Bioinformatics
|October 5, 2013
PubMed
Summary

This study introduces a generalized query-based active learning (GQAL) method to improve classifier accuracy in biological domains. GQAL constructs generalized queries from multiple instances, outperforming traditional methods in identifying differentially methylated regions and other datasets.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Ecological momentary assessment suggests greater sensitivity to clinical change in a compensatory strategy pilot clinical trial.

Archives of clinical neuropsychology : the official journal of the National Academy of Neuropsychologists·2026
Same author

Augmenting prion surveillance by immunohistochemistry using artificial intelligence-based image analysis.

Veterinary pathology·2026
Same author

Temperature discomfort impairs everyday cognition: a pilot study using smartwatch-based ecological momentary assessment.

Environmental research communications·2026
Same author

Promoting digital memory aid use in older adults with cognitive concerns: A pilot randomized controlled trial of adaptive web-based training.

Neuropsychology·2026
Same author

Environmental Transgenerational Epigenetics: Effects on Fertility and Offspring Health.

Advances in experimental medicine and biology·2026
Same author

Introductory editorial for a special issue on artificial intelligence in neuropsychology.

The Clinical neuropsychologist·2026

Area of Science:

  • Machine Learning
  • Bioinformatics
  • Genomics

Background:

  • Active learning is a supervised learning technique that reduces the need for labeled data.
  • Classified examples are often expensive and time-consuming to obtain in biological domains.
  • Traditional active learning methods query specific examples, which may contain irrelevant features, increasing the burden on human experts.

Purpose of the Study:

  • To propose a generalized query-based active learning (GQAL) approach for more efficient and accurate machine learning in biology.
  • To improve upon traditional active learning methods by constructing generalized queries from multiple instances.
  • To apply GQAL for the identification of differentially methylated regions (DMRs) and evaluate its performance on diverse datasets.

Main Methods:

More Related Videos

Genome-Wide Analysis of DNA Methylation in Gastrointestinal Cancer
07:50

Genome-Wide Analysis of DNA Methylation in Gastrointestinal Cancer

Published on: September 18, 2020

Methyl-binding DNA capture Sequencing for Patient Tissues
08:40

Methyl-binding DNA capture Sequencing for Patient Tissues

Published on: October 31, 2016

Related Experiment Videos

Last Updated: May 7, 2026

Comprehensive DNA Methylation Analysis Using a Methyl-CpG-binding Domain Capture-based Method in Chronic Lymphocytic Leukemia Patients
13:21

Comprehensive DNA Methylation Analysis Using a Methyl-CpG-binding Domain Capture-based Method in Chronic Lymphocytic Leukemia Patients

Published on: June 16, 2017

Genome-Wide Analysis of DNA Methylation in Gastrointestinal Cancer
07:50

Genome-Wide Analysis of DNA Methylation in Gastrointestinal Cancer

Published on: September 18, 2020

Methyl-binding DNA capture Sequencing for Patient Tissues
08:40

Methyl-binding DNA capture Sequencing for Patient Tissues

Published on: October 31, 2016

  • Developed a generalized query-based active learning (GQAL) algorithm.
  • Constructed generalized queries based on multiple instances to reduce feature relevance issues.
  • Applied GQAL to identify differentially DNA methylated regions (DMRs).
  • Evaluated GQAL performance against a popular active learning technique on 13 additional datasets.

Main Results:

  • The proposed GQAL approach achieved higher accuracy compared to traditional active learning methods.
  • GQAL demonstrated effectiveness in identifying differentially methylated regions (DMRs).
  • Performance evaluation on 13 datasets confirmed GQAL's superiority over another active learning technique.

Conclusions:

  • Generalized query-based active learning (GQAL) offers a more accurate and efficient approach for machine learning tasks in biology.
  • GQAL is particularly promising for domains like genomics, where data labeling is resource-intensive.
  • The method shows significant potential for applications such as identifying differentially methylated regions.